big data in agriculture : opportunities for data driven agronomy

39

Upload: decision-and-policy-analysis-program

Post on 14-Apr-2017

1.404 views

Category:

Science


1 download

TRANSCRIPT

Page 1: Big Data in Agriculture : Opportunities for data driven agronomy
Page 2: Big Data in Agriculture : Opportunities for data driven agronomy

Moore’s Law in Space

Page 3: Big Data in Agriculture : Opportunities for data driven agronomy
Page 4: Big Data in Agriculture : Opportunities for data driven agronomy

Internet usage:40% of global population – 2.26 billion

Developing countries: from 0-30% in 16 yearsOn linear trend, 100% in just 22 years. Goal of UN to have 50% by 2015. Achieved 34%

Philippines ranked above US in 2015

A game changer?

Page 5: Big Data in Agriculture : Opportunities for data driven agronomy
Page 6: Big Data in Agriculture : Opportunities for data driven agronomy
Page 7: Big Data in Agriculture : Opportunities for data driven agronomy

But is the Big Data revolution democratic?

Page 8: Big Data in Agriculture : Opportunities for data driven agronomy
Page 9: Big Data in Agriculture : Opportunities for data driven agronomy

Democratizing Big Data…..About CGIAR mission: propose ANOTHER BUSINESS MODEL for the use of these techniques.

Google, Monsanto, John Deere all entered the business of big data in Ag, but with the same business model: subscribed service for commercial farmers. Smallholders also have much to benefit from BD, but can’t always pay for the service.

How do we close equity gaps instead of widening them?

Page 10: Big Data in Agriculture : Opportunities for data driven agronomy

The VisionThe data revolution is changing the role, reach and modus operandi of research and development organizations. It represents an unprecedented opportunity to find new ways of reducing hunger and poverty, but also has its risks: unequal access to and use of information

How do we close equity gaps instead of widening them? We propose ANOTHER BUSINESS MODEL for the use of these techniques.

Page 11: Big Data in Agriculture : Opportunities for data driven agronomy

Goal: to harness the capabilities of Big Data to accelerate and enhance the impact of international agricultural research, and solve development problems faster, better and at greater scale

Organise: Make CGIAR + partners data truly open and available, revolutionize how agricultural data is collected and managedConvene: Bring big data to agriculture and agriculture to big data by partnering the CGIAR with 42 Big Data powerhouse partnersInspire: Solve development problems with big data; generate new international public goods around big data in agricultural development

Page 12: Big Data in Agriculture : Opportunities for data driven agronomy

Big Data: A behavior change• YES big data requires large amounts of data and therefore big

servers, BUT it is much more than that:• REUSING the data: Extracting embedded knowledge from existing

datasets to answer questions that don’t have to do with the initial purpose for which the data was captured.• COMBINING datasets that were originally not supposed to meet,

enable to relate more variables and uncover useful correlations.• ANALYZING with CREATIVITY: the data scientist needs to be

innovative in the uses he is giving the data. Who would have guessed that Google requests could help fighting flu?

Page 13: Big Data in Agriculture : Opportunities for data driven agronomy

Many partners: central to achieving breakthrough big data science

Page 14: Big Data in Agriculture : Opportunities for data driven agronomy
Page 15: Big Data in Agriculture : Opportunities for data driven agronomy

Data driven, climate smart agronomy

Page 16: Big Data in Agriculture : Opportunities for data driven agronomy

1.Avoid crop losses due to climate variability

2.Close yield gaps through appropriate management of the climate

3.Produce food sustainably, synergistically with the environment

Page 17: Big Data in Agriculture : Opportunities for data driven agronomy
Page 18: Big Data in Agriculture : Opportunities for data driven agronomy

Hey Cigi, when should I plant my maize?

Real-time decision support system for farmers

Easy natural language as an interface

Smart artificial intelligence trained by CGIAR and partners

Leveraging open, harmonized and interoperable multiple databases

Page 19: Big Data in Agriculture : Opportunities for data driven agronomy

A complementary bottom-up approach: Information from commercial fields - Taking advantage of modern information technologies !!!

Climate Soil Crop management Productivity

/Quality

Site-specific information

Yield and quality limiting factors

favorable/unfavorable Climatic patterns

Optimal site-specific management practices

Massively exciting, transformational science

“The most magical aspect of big data is Smart Data: the application of statistical analytics and machine learning to data sets to find interesting connections and signals in all the noise.” ”. Philip Brittan. http://tmsnrt.rs/1EmFXTT

Page 20: Big Data in Agriculture : Opportunities for data driven agronomy

Machine learning

Redes neuronales artificiales (supervisadas, no supervisadas )

Random Forest

Regresión lineal multiple (OLS)

Conditional Forest

Análisis factorials (PCA, MCA, CATPCA)

Modelo lineal generalizado (GLM)

Modelos mixtos

TraditionalLógica difusa

Density-based clustering

Page 21: Big Data in Agriculture : Opportunities for data driven agronomy

238 production events, 2013 to 2016www.open-aeps.org

From zero to heros: New insights in 4 slides

Page 22: Big Data in Agriculture : Opportunities for data driven agronomy

VARIABLES SIGNIFICADO TIPO UNIDADTIPO_SIEMBRA Siembra mecanizada o manual Categórica NASEM_TRATADAS Tratamiento de la semilla Booleana NADIST_SURCOS Distancia entre surcos Cuantitativa mDIST_PLANTAS Distancia entre plantas Cuantitativa mCOLOR_ENDOSPERMO Color del maíz Categórica NACULT_ANT Cultivo anterior Categórica NADRENAJE Se hace drenaje en la parcela Booleana NAPOBLACION_20DIAS Numero de plantas por hectárea vivas a los 20 días después de germinación Cuantitativa plantas.ha-1

METODO_COSECHA Cosecha mecanizada o manual Categórica NAALMACENAMIENTO_FINCA Se almacena la cosecha? Booleana NACONTENFQUI Conteo de tratamientos químicos contra enfermedades Cuantitativa NACONTMALQUI Conteo de tratamientos químicos contra malezas Cuantitativa NACONTPLAQUI Conteo de tratamientos químicos contra plagas Cuantitativa NACANFERQUI Conteo de fertilizaciones químicas Cuantitativa NAPENDIENTE Pendiente promedio del lote Cuantitativa gradosPH pH del suelo Cuantitativa NAESTRUCTURA_RASTA Estructura del suelo Categórica NAMAT_ORGANICA Contenido de materia orgánica Categórica NADRE_INTERN Capacidad de drenaje interno del suelo Categórica NADREN_EXTERN Capacidad de drenaje externo del suelo Categórica NAPROF_EFEC Profundidad efectiva del suelo Cuantitativa cmMATERIAL_GENETICO1 Cultivar Categórica NATEMP_MAX_AVG_VEG Promedio de temperatura máxima en fase vegetativa Cuantitativa °CTEMP_MIN_AVG_VEG Promedio de temperatura mínima en fase vegetativa Cuantitativa °CTEMP_AVG_VEG Promedio de temperatura en fase vegetativa Cuantitativa °CDIURNAL_RANGE_AVG_VEG Amplitud térmica promedio en fase vegetativa Cuantitativa °CSOL_ENER_ACCU_VEG Acumulación de energía solar en fase vegetativa Cuantitativa cal.cm-2

RAIN_ACCU_VEG Acumulación de precipitación en fase vegetativa Cuantitativa mmRAIN_10_FREQ_VEG Frecuencia de días con lluvias de más de 10mm en fase vegetativa Cuantitativa NATEMP_MIN_15_FREQ_VEG Frecuencia de días con temperaturas mínimas menores a 15°C en fase vegetativa Cuantitativa NARHUM_AVG_VEG Promedio de humedad relativa en fase vegetativa Cuantitativa %RHUM_SD_VEG Deviación estándar de la humedad relativa en fase vegetativa Cuantitativa NATEMP_MAX_AVG_FOR Promedio de temperatura máxima en fase de formación Cuantitativa °CTEMP_MIN_AVG_FOR Promedio de temperatura mínima en fase de formación Cuantitativa °CTEMP_AVG_FOR Promedio de temperatura en fase de formación Cuantitativa °CDIURNAL_RANGE_AVG_FOR Amplitud térmica promedio en fase de formación Cuantitativa °CSOL_ENER_ACCU_FOR Acumulación de energía solar en fase de formación Cuantitativa cal.cm-2

RAIN_ACCU_FOR Acumulación de precipitación en fase de formación Cuantitativa mmRAIN_10_FREQ_FOR Frecuencia de días con lluvias de más de 10mm en fase de formación Cuantitativa NATEMP_MIN_15_FREQ_FOR Frecuencia de días con temperaturas mínimas menores a 15°C en fase de formación Cuantitativa NARHUM_AVG_FOR Promedio de humedad relativa en fase de formación Cuantitativa %RHUM_SD_FOR Deviación estándar de la humedad relativa en fase de formación Cuantitativa NATEMP_MAX_AVG_MAD Promedio de temperatura máxima en fase de maduración Cuantitativa °CTEMP_MIN_AVG_MAD Promedio de temperatura mínima en fase de maduración Cuantitativa °CTEMP_AVG_MAD Promedio de temperatura en fase de maduración Cuantitativa °CDIURNAL_RANGE_AVG_MAD Amplitud térmica promedio en fase de maduración Cuantitativa °CSOL_ENER_ACCU_MAD Acumulación de energía solar en fase de maduración Cuantitativa cal.cm-2

RAIN_ACCU_MAD Acumulación de precipitación en fase de maduración Cuantitativa mmRAIN_10_FREQ_MAD Frecuencia de días con lluvias de más de 10mm en fase de maduración Cuantitativa NATEMP_MIN_15_FREQ_MAD Frecuencia de días con temperaturas mínimas menores a 15°C en fase de maduración Cuantitativa NARHUM_AVG_MAD Promedio de humedad relativa en fase de maduración Cuantitativa %RHUM_SD_MAD Deviación estándar de la humedad relativa en fase de maduración Cuantitativa NATOTN Cantidad total de nitrógeno aportada Cuantitativa kgTOTP Cantidad total de fosforo aportada Cuantitativa kgTOTK Cantidad total de potasio aportada Cuantitativa kgTEXTURA Textura del suelo Categórica NARDT Rendimiento Cuantitativa kg.ha-1

Varia

bles

Data and AnalysisFarmers record production data and

send through app

Data geeks mine it to death:• Conditional Inference Forest (CIF)1,2

• Partial dependence plots3

• ……..

1 Hothorn, Torsten, Kurt Hornik, and Achim Zeileis. 2006. “Unbiased Recursive Partitioning: A Conditional Inference Framework.” Journal of Computational and Graphical Statistics 15(3): 651–74.2 Strobl, Carolin, Anne-laure Boulesteix, Thomas Kneib, Thomas Augustin, and Achim Zeileis. 2008. “Conditional Variable Importance for Random Forests.” BMC Bioinformatics 11: 1–11.3 Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. 2009. “The Elements of Statistical Learning.” Elements 1: 337–87. http://www.springerlink.com/index/10.1007/b94608.

Page 23: Big Data in Agriculture : Opportunities for data driven agronomy

Results

(c)

(d)

(e)

(b)

(a)

R2 = 45.79

Slope (>3°) and de external drain ( at least slow ) = Associated with high yield.

25 kg/ha is the minimum phosphorus to exploit the plan potential. From the 238 events, only 23 (10%) apply more than 25 kg/ha of phosphorus and 198 not fertilized.

Change the harvest method from manual to mechanized can gain 100 kg/haHowever only 59 events (25%) are harvest with the combined method.

The plant population at 20 day after germination should be above the 65000 plants/haCurrently, 158 (66%) plots, have less than 70 000 plants Actualmente, En 158 (66%) lotes, hay menos de 70 000 plantas.ha-1 a los 20 días

Page 24: Big Data in Agriculture : Opportunities for data driven agronomy

Impact Farmer gets personalied “Fenalcheck” report

Five basic farming principles identified (CropCheck): Privileging plots with slope > 2° Farmers with plots without external

drainage should adapt them. Apply a minimum amount of

phosphorus around 25kg . Harvest using a combined method Assure the plant population will be

at least of 65000 plants/ha, 20 days after germination.

Yield distributions for the three agronomic management groups observed in Córdoba.

Vertical lines correspond with the yield average from each group, the red and blue arrows represent the

yield gap for the members of groups B and N.

Page 25: Big Data in Agriculture : Opportunities for data driven agronomy

MADR-CIAT-FEDEARROZ work won big data prize by UN

Page 26: Big Data in Agriculture : Opportunities for data driven agronomy

PROBABILISTIC PRECIPITATION FORECAST

33

33

33

AboveNormalBelow

38

31

31

2227

51

37

33

31

39

33

28

Agroclimatic Seasonal

forecasting

Page 27: Big Data in Agriculture : Opportunities for data driven agronomy

CañaPrecipitación - Guacarí

Precipitación - Aeropuerto

Valle del Cauca

DéficitNormalExceso

Precipitación - Tuluá

Ago Sep Oct Nov Dic Ene0

50

100

150

200

250

28.1

238.5

Promedio_Mensual Limite_Inferior

Prec

ipita

ción

(mm

)

Ago Sep Oct Nov Dic Ene0

50

100

150

200

250

15.544.9

93.5

Promedio_Mensual Limite_Inferior

Ago Sep Oct Nov Dic Ene0

50

100

150

200

250

7.1

45.8

Promedio_Mensual Limite_Inferior

Prec

ipita

ción

(mm

)

Ago Sep Oct Nov Dic Ene0

50

100

150

200

250

19.6

68.3

Promedio_Mensual Limite_Inferior Precipitación - Cenicaña

DéficitNormalExceso

DéficitNormalExceso

DéficitNormalExceso

Page 28: Big Data in Agriculture : Opportunities for data driven agronomy

Temperatura máxima (C) Precipitación (mm)

Lote Comercial / ESPINAL

Page 29: Big Data in Agriculture : Opportunities for data driven agronomy

5 May 25 May 19 Jun 14 Jul 08 Jul

Y el pronostico agroclimático? / ESPINAL

Sitios Piloto Sembrar Fedearroz 733

Reducir densidades de siembra si no puede garantizar suficiente agua

Si se decide por Fedearroz 2000 o Fedearroz 60 debería sembrara antes del 15 de Junio o debe garantizar riego para reducir el estrés por agua pero podrá presentar estrés por altas temperaturas y alta radiación

Page 30: Big Data in Agriculture : Opportunities for data driven agronomy

• Planting date = Last week of june (23 – 30)

• Variety = FEDEARROZ 733

• Fertilization F733 = Nitrogen: 75% during vegetative phase - 25% in reproductive phase.

• Water management = permanent saturation.

• Planting density = 110 Kg/ha.

Rrecommended management – August - Octuber

Pilot Plot / ESPINAL

Page 31: Big Data in Agriculture : Opportunities for data driven agronomy

Lote Comercial / ESPINAL

Temperatura máxima (C) Precipitación (mm)

300

76

116

Page 32: Big Data in Agriculture : Opportunities for data driven agronomy

5 May 25 May 19 Jun 14 Jul 08 Jul

Fedearroz 733: 6.860 kg/ha

Fedearroz 60: 4.600 kg/ha

Yield forecasts (ceiling)

Page 33: Big Data in Agriculture : Opportunities for data driven agronomy

Reunión 11 de Julio 2014

MERIDIANO DE CORDOBA: “Los arroceros de Córdoba que utilizan los Distritos de Riego de Mocarí y La Doctrina no sembraron, tal como se los aconsejó Fedearroz. En su momento se le presentó un modelo de simulación de los rendimientos que tendría el cultivo ante la menor oferta de lluvia, menos luminosidad y mayor humedad en el ambiente”.

Irrigation district of Mocarí and La Doctrina : 170 farmers covering 1.800 Ha decided not to plant paddy rice in Córdoba due to non optimal climate factors and reduced wáter availability. US$3.5m of input costs were saved – those who did plant lost their crop.

Montería

Page 34: Big Data in Agriculture : Opportunities for data driven agronomy

Historical profiling

Page 35: Big Data in Agriculture : Opportunities for data driven agronomy

Seasonal forecast

March-May 2014

Combining seasonal forecasts with empirical big data analysis

Variety Yield (Kg/Ha) No. of productive eventsF174 4,564 31FORTALEZA 3,543 17F2000 4,977 8LAGUNAS 5,052 6MOCARI 4,604 6

Belongs to Cluster 7

From 506 productive events in this region of Colombia, we identified 24 “homologous” clusters

Page 36: Big Data in Agriculture : Opportunities for data driven agronomy
Page 37: Big Data in Agriculture : Opportunities for data driven agronomy

Aplicativo móvil Plataforma web

Agricultural Extension SEXY again

Page 38: Big Data in Agriculture : Opportunities for data driven agronomy

Closing the information loop

• Use of ICTs to deliver recommendations back to farmers

• Use other means of communicating results:• Rural radio (28 channels

broadcasting recommendations in Colombia, weekly)

• Extension agents and rural agro-advisory systems

Page 39: Big Data in Agriculture : Opportunities for data driven agronomy

39

Stepwise development in agriculture

Años

T ha

201x19XX

Imported technology

Locally adapted agronomy

Data driven agronomy and technology development

Locally adapted technology